xen-devel.lists.xenproject.org archive mirror
 help / color / mirror / Atom feed
* VMX status report. Xen:25929 & Dom0:3.5.4
@ 2012-09-24  6:17 Wu, GabrielX
  2012-09-24 13:16 ` Konrad Rzeszutek Wilk
  0 siblings, 1 reply; 3+ messages in thread
From: Wu, GabrielX @ 2012-09-24  6:17 UTC (permalink / raw)
  To: xen-devel@lists.xen.org
  Cc: Ren, Yongjie, Liu, RongrongX, Liu, SongtaoX, Zhou, Chao

Hi all,

This is the test report of xen-unstable tree, no issue found and two issues fixed.

Version Info:
=================================================================
xen-changeset:   25929:fee83ac77d8c
Dom0:          linux.git  3.5.4
=================================================================

New issue(0)
==============

Fixed issues(2)
==============
1. RHEL6.2/6.1 guest runs quite slow
  http://bugzilla.xen.org/bugzilla/show_bug.cgi?id=1811
2. XenU PV guest with VIF network cannot boot up with Linux3.6 dom0
  http://bugzilla.xen.org/bugzilla/show_bug.cgi?id=1832

Old issues(9)
==============
1. [ACPI] System cann't resume after do suspend
  http://bugzilla.xen.org/bugzilla/show_bug.cgi?id=1707
2. [XL]"xl vcpu-set" causes dom0 crash or panic
  http://bugzilla.xen.org/bugzilla/show_bug.cgi?id=1730
3. [VT-D]fail to detach NIC from guest  
  http://bugzilla.xen.org/bugzilla/show_bug.cgi?id=1736
4. Sometimes Xen panic on ia32pae Sandybridge when restore guest
  http://bugzilla.xen.org/bugzilla/show_bug.cgi?id=1747
5. after detaching a VF from a guest, shutdown the guest is very slow
  http://bugzilla.xen.org/bugzilla/show_bug.cgi?id=1812
6. Poor performance when do guest save/restore and migration with linux 3.1 dom0
  http://bugzilla.xen.org/bugzilla/show_bug.cgi?id=1784
7. vcpu-set doesn't take effect on guest
  http://bugzilla.xen.org/bugzilla/show_bug.cgi?id=1822
8.Fail to probe NIC driver in domu
  http://bugzilla.xen.org/bugzilla/show_bug.cgi?id=1824
9. Dom0 cannot be shutdown before PCI device detachment from guest
  http://bugzilla.xen.org/bugzilla/show_bug.cgi?id=1826


Best Regards,
Ronghui Wu(Gabriel)

^ permalink raw reply	[flat|nested] 3+ messages in thread

* Re: VMX status report. Xen:25929 & Dom0:3.5.4
  2012-09-24  6:17 VMX status report. Xen:25929 & Dom0:3.5.4 Wu, GabrielX
@ 2012-09-24 13:16 ` Konrad Rzeszutek Wilk
  2012-09-25  5:41   ` Ren, Yongjie
  0 siblings, 1 reply; 3+ messages in thread
From: Konrad Rzeszutek Wilk @ 2012-09-24 13:16 UTC (permalink / raw)
  To: Wu, GabrielX
  Cc: Zhou, Chao, Ren, Yongjie, Liu, SongtaoX, Liu, RongrongX,
	xen-devel@lists.xen.org

On Mon, Sep 24, 2012 at 06:17:33AM +0000, Wu, GabrielX wrote:
> Hi all,
> 
> This is the test report of xen-unstable tree, no issue found and two issues fixed.

Wohoo! Great!
> 
> Version Info:
> =================================================================
> xen-changeset:   25929:fee83ac77d8c
> Dom0:          linux.git  3.5.4
> =================================================================
> 
> New issue(0)
> ==============
> 
> Fixed issues(2)
> ==============
> 1. RHEL6.2/6.1 guest runs quite slow
>   http://bugzilla.xen.org/bugzilla/show_bug.cgi?id=1811
> 2. XenU PV guest with VIF network cannot boot up with Linux3.6 dom0
>   http://bugzilla.xen.org/bugzilla/show_bug.cgi?id=1832
> 
> Old issues(9)
> ==============
> 1. [ACPI] System cann't resume after do suspend
>   http://bugzilla.xen.org/bugzilla/show_bug.cgi?id=1707
> 2. [XL]"xl vcpu-set" causes dom0 crash or panic
>   http://bugzilla.xen.org/bugzilla/show_bug.cgi?id=1730
> 3. [VT-D]fail to detach NIC from guest  
>   http://bugzilla.xen.org/bugzilla/show_bug.cgi?id=1736
> 4. Sometimes Xen panic on ia32pae Sandybridge when restore guest
>   http://bugzilla.xen.org/bugzilla/show_bug.cgi?id=1747
> 5. after detaching a VF from a guest, shutdown the guest is very slow
>   http://bugzilla.xen.org/bugzilla/show_bug.cgi?id=1812
> 6. Poor performance when do guest save/restore and migration with linux 3.1 dom0
>   http://bugzilla.xen.org/bugzilla/show_bug.cgi?id=1784

Added some questions in the bug.
> 7. vcpu-set doesn't take effect on guest
>   http://bugzilla.xen.org/bugzilla/show_bug.cgi?id=1822
> 8.Fail to probe NIC driver in domu
>   http://bugzilla.xen.org/bugzilla/show_bug.cgi?id=1824
> 9. Dom0 cannot be shutdown before PCI device detachment from guest
>   http://bugzilla.xen.org/bugzilla/show_bug.cgi?id=1826

The same - added some questions that I believe I asked on the mailing
list last time.
> 
> 
> Best Regards,
> Ronghui Wu(Gabriel)
> 
> _______________________________________________
> Xen-devel mailing list
> Xen-devel@lists.xen.org
> http://lists.xen.org/xen-devel
> 

^ permalink raw reply	[flat|nested] 3+ messages in thread

* Re: VMX status report. Xen:25929 & Dom0:3.5.4
  2012-09-24 13:16 ` Konrad Rzeszutek Wilk
@ 2012-09-25  5:41   ` Ren, Yongjie
  0 siblings, 0 replies; 3+ messages in thread
From: Ren, Yongjie @ 2012-09-25  5:41 UTC (permalink / raw)
  To: Konrad Rzeszutek Wilk, Wu, GabrielX
  Cc: Liu, RongrongX, Liu, SongtaoX, Zhou, Chao,
	xen-devel@lists.xen.org

> -----Original Message-----
> From: Konrad Rzeszutek [mailto:ketuzsezr@gmail.com] On Behalf Of
> Konrad Rzeszutek Wilk
> Sent: Monday, September 24, 2012 9:16 PM
> To: Wu, GabrielX
> Cc: xen-devel@lists.xen.org; Ren, Yongjie; Liu, RongrongX; Liu, SongtaoX;
> Zhou, Chao
> Subject: Re: [Xen-devel] VMX status report. Xen:25929 & Dom0:3.5.4
> 
> > 6. Poor performance when do guest save/restore and migration with
> linux 3.1 dom0
> >   http://bugzilla.xen.org/bugzilla/show_bug.cgi?id=1784
> 
> Added some questions in the bug.


Output of "perf stat xl migrate 1 localhost" for localhost migration.

      87086.962947 task-clock                #    0.964 CPUs utilized
           132,882 context-switches          #    0.002 M/sec 
            10,252 CPU-migrations            #    0.000 M/sec 
            18,159 page-faults               #    0.000 M/sec 
     <not counted> cycles                  
     <not counted> stalled-cycles-frontend 
     <not counted> stalled-cycles-backend  
     <not counted> instructions            
     <not counted> branches                
     <not counted> branch-misses           

      90.299519242 seconds time elapsed

BTW, do you know why the last 6 counter didn't have data?
Only met this issue when running 'perf stat' command in Dom0.

The following is the output of "perf record -e cpu-clock xl migrate 1 localhost" command.

[ perf record: Woken up 10 times to write data ]
[ perf record: Captured and wrote 3.321 MB perf.data (~145093 samples) ]
# Events: 86K cpu-clock
#
# Overhead          Command          Shared Object                            Symbol
# ........  ...............  .....................  ................................
#
    32.08%  libxl-save-help  [kernel.kallsyms]      [k] hypercall_page
    27.42%              ssh  libcrypto.so.1.0.0     [.] 0x7a6ba         
    14.73%  libxl-save-help  [kernel.kallsyms]      [k] smp_call_function_many
     4.51%              ssh  libcrypto.so.1.0.0     [.] md5_block_asm_data_order
     4.19%              ssh  ssh                    [.] 0x28af6         
     1.83%              ssh  [kernel.kallsyms]      [k] hypercall_page
     1.44%              ssh  libcrypto.so.1.0.0     [.] AES_encrypt
     1.32%  libxl-save-help  [kernel.kallsyms]      [k] find_next_bit
     0.81%  libxl-save-help  [kernel.kallsyms]      [k] xen_send_IPI_one
     0.78%  libxl-save-help  [kernel.kallsyms]      [k] pvclock_clocksource_read
     0.71%  libxl-save-help  [kernel.kallsyms]      [k] unmap_single_vma
     0.66%              ssh  [kernel.kallsyms]      [k] copy_user_generic_string
     0.51%  libxl-save-help  [kernel.kallsyms]      [k] xen_vcpu_stolen
     (didn't include other more lines.)
Also, added update in the bugzilla.


> > 7. vcpu-set doesn't take effect on guest
> >   http://bugzilla.xen.org/bugzilla/show_bug.cgi?id=1822
> > 8.Fail to probe NIC driver in domu
> >   http://bugzilla.xen.org/bugzilla/show_bug.cgi?id=1824
> > 9. Dom0 cannot be shutdown before PCI device detachment from guest
> >   http://bugzilla.xen.org/bugzilla/show_bug.cgi?id=1826
> 
> The same - added some questions that I believe I asked on the mailing
> list last time.
my fault. I'll reply to the email thread you asked me the question.

^ permalink raw reply	[flat|nested] 3+ messages in thread

end of thread, other threads:[~2012-09-25  5:41 UTC | newest]

Thread overview: 3+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2012-09-24  6:17 VMX status report. Xen:25929 & Dom0:3.5.4 Wu, GabrielX
2012-09-24 13:16 ` Konrad Rzeszutek Wilk
2012-09-25  5:41   ` Ren, Yongjie

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).